Domain Adaptation Through Synthesis for Unsupervised Person Re-identification

  • Sławomir BąkEmail author
  • Peter Carr
  • Jean-François Lalonde
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11217)


Drastic variations in illumination across surveillance cameras make the person re-identification problem extremely challenging. Current large scale re-identification datasets have a significant number of training subjects, but lack diversity in lighting conditions. As a result, a trained model requires fine-tuning to become effective under an unseen illumination condition. To alleviate this problem, we introduce a new synthetic dataset that contains hundreds of illumination conditions. Specifically, we use 100 virtual humans illuminated with multiple HDR environment maps which accurately model realistic indoor and outdoor lighting. To achieve better accuracy in unseen illumination conditions we propose a novel domain adaptation technique that takes advantage of our synthetic data and performs fine-tuning in a completely unsupervised way. Our approach yields significantly higher accuracy than semi-supervised and unsupervised state-of-the-art methods, and is very competitive with supervised techniques.


Synthetic Identification Unsupervised Domain adaptation 

Supplementary material

474201_1_En_12_MOESM1_ESM.m4v (12.9 mb)
Supplementary material 1 (m4v 13161 KB)
474201_1_En_12_MOESM2_ESM.m4v (12.8 mb)
Supplementary material 2 (m4v 13115 KB)
474201_1_En_12_MOESM3_ESM.mp4 (44.5 mb)
Supplementary material 3 (mp4 45562 KB)


  1. 1.
    Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006)CrossRefGoogle Scholar
  2. 2.
    Bak, S., Carr, P.: One-shot metric learning for person re-identification. In: CVPR, June 2017Google Scholar
  3. 3.
    Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: CVPR, July 2017Google Scholar
  4. 4.
    Cheng, D., Gong, Y., Zhou, S., Wang, J., Zheng, N.: Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: CVPR, June 2016Google Scholar
  5. 5.
    Debevec, P.: Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography. In: Proceedings of ACM SIGGRAPH, pp. 189–198 (1998)Google Scholar
  6. 6.
    Deng, W., Zheng, L., Kang, G., Yang, Y., Ye, Q., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: CVPR (2018)Google Scholar
  7. 7.
    Dibra, E., Maye, J., Diamanti, O., Siegwart, R., Beardsley, P.: Extending the performance of human classifiers using a viewpoint specific approach. In: WACV (2015)Google Scholar
  8. 8.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV (2013)Google Scholar
  9. 9.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)Google Scholar
  10. 10.
    Gao, S., Tsang, I.W.H., Chia, L.T., Zhao, P.: Local features are not lonely–laplacian sparse coding for image classification. In: CVPR (2010)Google Scholar
  11. 11.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)Google Scholar
  12. 12.
    Gou, M., Karanam, S., Liu, W., Camps, O., Radke, R.J.: DukeMTMC4ReID: a large-scale multi-camera person re-identification dataset. In: CVPRW (2017)Google Scholar
  13. 13.
    Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: PETS (2007)Google Scholar
  14. 14.
    Hattori, H., Boddeti, Y.V.N., Kitani, K.M., Kanade, T.: Learning scene-specific pedestrian detectors without real data. In: CVPR (2015)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, June 2016Google Scholar
  16. 16.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arxiv (2017)Google Scholar
  17. 17.
    Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 91–102. Springer, Heidelberg (2011). Scholar
  18. 18.
    Hu, J., Lu, J., Tan, Y.P.: Deep transfer metric learning. In: CVPR (2015)Google Scholar
  19. 19.
    Huang, S., Ramanan, D.: Expecting the unexpected: training detectors for unusual pedestrians with adversarial imposters. In: CVPR (2017)Google Scholar
  20. 20.
    Kodirov, E., Xiang, T., Fu, Z., Gong, S.: Person re-identification by unsupervised \(\ell _1\) graph learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 178–195. Springer, Cham (2016). Scholar
  21. 21.
    Kodirov, E., Xiang, T., Gong, S.: Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification. In: BMVC (2015)Google Scholar
  22. 22.
    Li, D., Chen, X., Zhang, Z., Huang, K.: Learning deep context-aware features over body and latent parts for person re-identification. In: CVPR, July 2017Google Scholar
  23. 23.
    Li, S., Bak, S., Carr, P., Wang, X.: Diversity regularized spatiotemporal attention for video-based person re-identification. In: CVPR, June 2018Google Scholar
  24. 24.
    Li, W., Zhao, R., Wang, X.: Human reidentification with transferred metric learning. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 31–44. Springer, Heidelberg (2013). Scholar
  25. 25.
    Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: Deep filter pairing neural network for person re-identification. In: CVPR (2014)Google Scholar
  26. 26.
    Li, Z., Chang, S., Liang, F., Huang, T., Cao, L., Smith, J.: Learning locally-adaptive decision functions for person verification. In: CVPR (2013)Google Scholar
  27. 27.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: CVPR (2015)Google Scholar
  28. 28.
    Liu, X., Song, M., Tao, D., Zhou, X., Chen, C., Bu, J.: Semi-supervised coupled dictionary learning for person re-identification. In: CVPR, June 2014Google Scholar
  29. 29.
    Matsukawa, T., Okabe, T., Suzuki, E., Sato, Y.: Hierarchical gaussian descriptor for person re-identification. In: CVPR, June 2016Google Scholar
  30. 30.
    McCormac, J., Handa, A., Leutenegger, S., Davison, A.J.: SceneNet RGB-D: can 5m synthetic images beat generic imagenet pre-training on indoor segmentation? In: ICCV, October 2017Google Scholar
  31. 31.
    Paisitkriangkrai, S., Shen, C., van den Hengel, A.: Learning to rank in person re-identification with metric ensembles. In: CVPR (2015)Google Scholar
  32. 32.
    Peng, P., et al.: Unsupervised cross-dataset transfer learning for person re-identification. In: CVPR, June 2016Google Scholar
  33. 33.
    Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016). Scholar
  34. 34.
    Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: CVPR (2016)Google Scholar
  35. 35.
    Shi, Z., Hospedales, T.M., Xiang, T.: Transferring a semantic representation for person re-identification and search. In: CVPR (2015)Google Scholar
  36. 36.
    Shotton, J., et al.: Efficient human pose estimation from single depth images. TPAMI 35(12), 2821–2840 (2013)CrossRefGoogle Scholar
  37. 37.
    Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: CVPR (2017)Google Scholar
  38. 38.
    Su, C., Zhang, S., Xing, J., Gao, W., Tian, Q.: Deep attributes driven multi-camera person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 475–491. Springer, Cham (2016). Scholar
  39. 39.
    Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. In: arXiv preprint (2016)Google Scholar
  40. 40.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)Google Scholar
  41. 41.
    Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: ICCV (2015)Google Scholar
  42. 42.
    Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR (2018)Google Scholar
  43. 43.
    Xiao, T., Li, H., Ouyang, W., Wang, X.: Learning deep feature representations with domain guided dropout for person re-identification. In: CVPR (2016)Google Scholar
  44. 44.
    Yu, H.X., Wu, A., Zheng, W.S.: Cross-view asymmetric metric learning for unsupervised person re-identification. In: ICCV (2017)Google Scholar
  45. 45.
    Zhang, L., Xiang, T., Gong, S.: Learning a discriminative null space for person re-identification. In: CVPR (2016)Google Scholar
  46. 46.
    Zhao, H., et al.: Spindle net: person re-identification with human body region guided feature decomposition and fusion. In: CVPR (2017)Google Scholar
  47. 47.
    Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 868–884. Springer, Cham (2016). Scholar
  48. 48.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)Google Scholar
  49. 49.
    Zheng, W.S., Gong, S., Xiang, T.: Towards open-world person re-identification by one-shot group-based verification. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 591–606 (2016)CrossRefGoogle Scholar
  50. 50.
    Zheng, W.S., Gong, S., Xiang, T.: Associating groups of people. In: BMVC (2009)Google Scholar
  51. 51.
    Zheng, W.S., Gong, S., Xiang, T.: Person re-identification by probabilistic relative distance comparison. In: CVPR (2011)Google Scholar
  52. 52.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Argo AIPittsburghUSA
  2. 2.Université LavalQuebec CityCanada

Personalised recommendations